When the Small-Loss Trick is Not Enough: Multi-Label Image Classification with Noisy Labels Applied to CCTV Sewer Inspections

TL;DR

This paper addresses the challenge of label noise in multi-label image classification for CCTV sewer inspections, proposing a novel hybrid sample selection method that outperforms existing approaches in noisy environments.

Contribution

The paper introduces MHSS, a new hybrid sample selection method tailored for noisy multi-label classification, improving automation in sewer inspection tasks.

Findings

MHSS outperforms existing methods on synthetic and real noisy data

Hybrid sample selection is more effective than small-loss tricks alone

Adapting methods from single-label to multi-label noise handling is beneficial

Abstract

The maintenance of sewerage networks, with their millions of kilometers of pipe, heavily relies on efficient Closed-Circuit Television (CCTV) inspections. Many promising approaches based on multi-label image classification have leveraged databases of historical inspection reports to automate these inspections. However, the significant presence of label noise in these databases, although known, has not been addressed. While extensive research has explored the issue of label noise in singlelabel classification (SLC), little attention has been paid to label noise in multi-label classification (MLC). To address this, we first adapted three sample selection SLC methods (Co-teaching, CoSELFIE, and DISC) that have proven robust to label noise. Our findings revealed that sample selection based solely on the small-loss trick can handle complex label noise, but it is sub-optimal. Adapting hybrid sample selection methods to noisy MLC appeared to be a more promising approach. In light of this, we developed a novel method named MHSS (Multi-label Hybrid Sample Selection) based on CoSELFIE. Through an in-depth comparative study, we demonstrated the superior performance of our approach in dealing with both synthetic complex noise and real noise, thus contributing to the ongoing efforts towards effective automation of CCTV sewer pipe inspections.